readable AI benchmarks (simplified)

readable AI benchmarks

IBM

Granite 4.0 Micro

non-reasoning · open weights · Sep 22, 2025

Granite 4.0 Micro has a Quality Score of 9.5, ranking 551st among 571 scored models. It has a 128k token context window. Its Reliability Score is 11.2, ranking 555th among 573 scored models, below average (total average: 36.5).

Quality Score9.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability11.2
Cache Discountnot available

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
128k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
not available
Output
not available
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
5.1
Coding
not available
Agentic
not available
Omniscience
-77.5
Correct
9.3%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 96.2%

Correct 9.3%Incorrect 86.8%Partial / not attempted 3.8%

Artificial Analysis benchmarks

Humanity’s Last Exam
5%
GPQA Diamond
34%
CritPt
0%
AA-Omniscience
11%
AA-LCR
7%

Similar models

Support me! Patreon